[PATCH] crypto: x86 - exit fpu context earlier in ECB/CBC macros

[Peter Lafreniere <peter@n8pjl.ca>]

Currently the ecb/cbc macros hold fpu context unnecessarily when using 
scalar cipher routines (e.g. when handling odd sizes of blocks per walk).

Change the macros to drop fpu context as soon as the fpu is out of use.

No performance impact found (on Intel Haswell).

Signed-off-by: Peter Lafreniere <peter@n8pjl.ca>
---
 arch/x86/crypto/ecb_cbc_helpers.h | 19 +++++++++++++++----
 1 file changed, 15 insertions(+), 4 deletions(-)

diff --git a/arch/x86/crypto/ecb_cbc_helpers.h b/arch/x86/crypto/ecb_cbc_helpers.h
index eaa15c7b29d6..b83085e18ab0 100644
--- a/arch/x86/crypto/ecb_cbc_helpers.h
+++ b/arch/x86/crypto/ecb_cbc_helpers.h
@@ -14,12 +14,13 @@
 #define ECB_WALK_START(req, bsize, fpu_blocks) do {			\
 	void *ctx = crypto_skcipher_ctx(crypto_skcipher_reqtfm(req));	\
+	const int __fpu_blocks = (fpu_blocks);				\
 	const int __bsize = (bsize);					\
 	struct skcipher_walk walk;					\
 	int err = skcipher_walk_virt(&walk, (req), false);		\
 	while (walk.nbytes > 0) {					\
 		unsigned int nbytes = walk.nbytes;			\
-		bool do_fpu = (fpu_blocks) != -1 &&			\
-			      nbytes >= (fpu_blocks) * __bsize;		\
+		bool do_fpu = __fpu_blocks != -1 &&			\
+			      nbytes >= __fpu_blocks * __bsize;		\
 		const u8 *src = walk.src.virt.addr;			\
 		u8 *dst = walk.dst.virt.addr;				\
 		u8 __maybe_unused buf[(bsize)];				\
@@ -35,7 +36,12 @@
 } while (0)
 
 #define ECB_BLOCK(blocks, func) do {					\
-	while (nbytes >= (blocks) * __bsize) {				\
+	const int __blocks = (blocks);					\
+	if (do_fpu && __blocks < __fpu_blocks) {			\
+		kernel_fpu_end();					\
+		do_fpu = false;						\
+	}								\
+	while (nbytes >= __blocks * __bsize) {				\
 		(func)(ctx, dst, src);					\
 		ECB_WALK_ADVANCE(blocks);				\
 	}								\
@@ -53,7 +59,12 @@
 } while (0)
 
 #define CBC_DEC_BLOCK(blocks, func) do {				\
-	while (nbytes >= (blocks) * __bsize) {				\
+	const int __blocks = (blocks);					\
+	if (do_fpu && __blocks <  __fpu_blocks) {			\
+		kernel_fpu_end();					\
+		do_fpu = false;						\
+	}								\
+	while (nbytes >= __blocks * __bsize) {				\
 		const u8 *__iv = src + ((blocks) - 1) * __bsize;	\
 		if (dst == src)						\
 			__iv = memcpy(buf, __iv, __bsize);		\
-- 
2.39.0